Atlas

Benchmarks

← All benchmarks

Arena Search (Style Controlled)

Search

Style-controlled Search Arena rating for assistants using integrated web search. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.

Top models (higher is better)

ModelScore
GPT-5.6 Sol1258
GPT-6.1 Sol1250
GPT-6 Astra1246
Claude Fable 5.11233
Claude Fable 51229
GPT-6 Sol1228
Claude Opus 51214
Claude Opus 5.51211
Opus 4.71210
GPT-6 Luna1209
Grok 4.51206
Opus 4.81195
Grok 4.31193
ERNIE 5.11192
Gemini 3 Flash Preview1189
GPT-51188
Grok 4 Fast1161
Loading Atlas data…